Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    closing braces and other syntax elements in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Efq
    -1.18
     Theſe
    -1.09
    expandindo
    -1.09
     myſelf
    -1.04
     виправивши
    -1.00
    AddTagHelper
    -1.00
     Daß
    -0.99
     becauſe
    -0.97
     Anſ
    -0.96
     Monfieur
    -0.96
    POSITIVE LOGITS
    .
    0.56
    ↵↵
    0.51
     
    0.50
     —
    0.48
    ,
    0.47
    <eos>
    0.47
    :
    0.46
     T
    0.45
     --
    0.44
    ↵
    0.44
    Act Density 0.224%

    No Known Activations